Light-X: Generative 4D Video Rendering with Camera and Illumination Control
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918248738455552 |
|---|---|
| author | Liu, Tianqi Chen, Zhaoxi Huang, Zihao Xu, Shaocong Zhang, Saining Ye, Chongjie Li, Bohan Cao, Zhiguo Li, Wei Zhao, Hao Liu, Ziwei |
| author_facet | Liu, Tianqi Chen, Zhaoxi Huang, Zihao Xu, Shaocong Zhang, Saining Ye, Chongjie Li, Bohan Cao, Zhiguo Li, Wei Zhao, Hao Liu, Ziwei |
| contents | Recent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighting, a key step toward generative modeling of real-world scenes is the joint control of camera trajectory and illumination, since visual dynamics are inherently shaped by both geometry and lighting. To this end, we present Light-X, a video generation framework that enables controllable rendering from monocular videos with both viewpoint and illumination control. 1) We propose a disentangled design that decouples geometry and lighting signals: geometry and motion are captured via dynamic point clouds projected along user-defined camera trajectories, while illumination cues are provided by a relit frame consistently projected into the same geometry. These explicit, fine-grained cues enable effective disentanglement and guide high-quality illumination. 2) To address the lack of paired multi-view and multi-illumination videos, we introduce Light-Syn, a degradation-based pipeline with inverse-mapping that synthesizes training pairs from in-the-wild monocular footage. This strategy yields a dataset covering static, dynamic, and AI-generated scenes, ensuring robust training. Extensive experiments show that Light-X outperforms baseline methods in joint camera-illumination control and surpasses prior video relighting methods under both text- and background-conditioned settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05115 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Light-X: Generative 4D Video Rendering with Camera and Illumination Control Liu, Tianqi Chen, Zhaoxi Huang, Zihao Xu, Shaocong Zhang, Saining Ye, Chongjie Li, Bohan Cao, Zhiguo Li, Wei Zhao, Hao Liu, Ziwei Computer Vision and Pattern Recognition Recent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighting, a key step toward generative modeling of real-world scenes is the joint control of camera trajectory and illumination, since visual dynamics are inherently shaped by both geometry and lighting. To this end, we present Light-X, a video generation framework that enables controllable rendering from monocular videos with both viewpoint and illumination control. 1) We propose a disentangled design that decouples geometry and lighting signals: geometry and motion are captured via dynamic point clouds projected along user-defined camera trajectories, while illumination cues are provided by a relit frame consistently projected into the same geometry. These explicit, fine-grained cues enable effective disentanglement and guide high-quality illumination. 2) To address the lack of paired multi-view and multi-illumination videos, we introduce Light-Syn, a degradation-based pipeline with inverse-mapping that synthesizes training pairs from in-the-wild monocular footage. This strategy yields a dataset covering static, dynamic, and AI-generated scenes, ensuring robust training. Extensive experiments show that Light-X outperforms baseline methods in joint camera-illumination control and surpasses prior video relighting methods under both text- and background-conditioned settings. |
| title | Light-X: Generative 4D Video Rendering with Camera and Illumination Control |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.05115 |